© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenAI · Weight-Sparse Transformers
    5. CircuitGPT-Python
    7. Residual Stream
    9. 7-RESID
    11. 718
    Prev
    Next
    INDEX
    Explanations

    special method names (negative activations)

    python-code · gemini-2.5-flash-lite

    isalpha method call

    python-code · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 256 tokens each
    Dataset (Dashboard)
    neuronpedia/python-code-simplified
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     an
    -0.21
     a
    -0.16
     two
    -0.16
    one
    -0.11
     out
    -0.07
     True
    -0.07
     variables
    -0.07
     any
    -0.07
     th
    -0.05
     di
    -0.04
    POSITIVE LOGITS
     function
    0.08
     range
    0.07
     us
    0.07
     ob
    0.07
     based
    0.06
     match
    0.05
    '
    0.00
    #
    0.00
    &
    0.00
    %
    0.00
    Activations Density 99.873%

    No Known Activations